Research map / Probabilistic and scientific modeling / Molecules and proteins
Predicting mutational effects on protein-protein binding via a side-chain diffusion probabilistic model
Shiwei Liu, Tian Zhu, Milong Ren, Yu Chungong, Dongbo Bu, Haicang Zhang
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add SidechainDiff pretrained representations to the ddG predictor (ablation) | DiffAffinity · SKEMPI2 all mutations | Pearson: 0.646 -> 0.669 | Improved |
| add SidechainDiff pretrained representations to the ddG predictor (ablation) | DiffAffinity · SARS-CoV-2 RBD binding affinity | Pearson: 0.295 -> 0.466 | Improved |
| add SidechainDiff representations (ablation) | DiffAffinity · SKEMPI2 multiple mutations | Pearson: 0.613 -> 0.650 | Improved |
| use linear projection of SidechainDiff representation instead of IPA predictor head (ablation) | DiffAffinity · SKEMPI2 all mutations | Pearson: 0.669 -> 0.326 | Hurt |
| replace RDE flow-based representation with SidechainDiff diffusion representation | ddG predictor · SKEMPI2 all mutations | Pearson: 0.632 -> 0.669 | Improved |
| replace ESM2 language model representation with SidechainDiff | ddG predictor · SKEMPI2 all mutations | Pearson: 0.623 -> 0.669 | Improved |
| replace RDE with SidechainDiff for side-chain packing | side-chain packing · PDB-REDO | steric clash number: 34.41 -> 27.70 | Improved |
| replace RDE with SidechainDiff for side-chain packing | side-chain packing · PDB-REDO | average chi MAE: 21.99 -> 22.06 | No clear effect |
| higher structural constraint (contact number 1-7 vs 11-19) | SidechainDiff · PDB-REDO side-chain packing | average chi error: 28.70 -> 15.43 | Improved |
Closest papers by meaning
- Sidechain conditioning and modeling for full-atom protein sequence design with FAMPNN (ICML 2025 · similarity 0.88)
- Enhancing Protein Mutation Effect Prediction through a Retrieval-Augmented Framework (NeurIPS 2024 · similarity 0.86)
- Predicting mutational effects on protein binding from folding energy (ICML 2025 · similarity 0.86)
- MutaPLM: Protein Language Modeling for Mutation Explanation and Engineering (NeurIPS 2024 · similarity 0.86)
- BindGPT: A Scalable Framework for 3D Molecular Design via Language Modeling and Reinforcement Learning (AAAI 2025 · similarity 0.85)
- 4D Diffusion for Dynamic Protein Structure Prediction with Reference and Motion Guidance (AAAI 2025 · similarity 0.85)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
